v2.2.256: 코어 채팅 큰 입력 청킹·통합 + 실제 컨텍스트 창 정렬 + 모델 핸들 race 수정

큰 입력 시 "Failed to acquire LM Studio model handle … Operation canceled"
로 턴 전체가 죽던 문제를 3계층으로 해결. 일반 채팅(코어 경로)은 그동안
단일 예산 호출이라 약한 모델·큰 입력에서 무너졌다 — 그 갭을 메움.

- 핸들 race 수정: getModelHandle 을 재시도 루프 안으로 이동. 취소/죽은-핸들
  류 에러는 SDK 재생성 후 1회 자동 재시도(실제 사용자 취소는 존중). 라이프
  사이클의 동시 로드가 abort 되며 SDK 가 coalesce 한 JIT 조회까지 죽던 것.
- Phase 1 실제 창 정렬: llm.getContextLength()(캐시)로 실측 창에 예산 클램프.
  설정값보다 작은 창으로 로드된 경우 서버 truncation/빈 답변 차단. 배지에 표시.
- Phase 2 코어 Map-Reduce: 단일 입력이 (유효 창 × ratio) 초과 시 청크→질의
  인지형 추출→통합. 부분/전체 폴백, 무관 시 정직 신호. 동시성 기본 2.
- Phase 3 메타 노출: 진행/결과 배지 표시, [조각 k] 출처 옵트인.

신규 설정 5종. /meet·/review 전용 경로는 불변. 테스트 +25건, 전체 684 통과.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-19 18:05:44 +09:00
parent 6adbc2a6fa
commit 76d5fedfb5
13 changed files with 883 additions and 19 deletions
+94
View File
@@ -140,6 +140,7 @@ export { _parseTaskAttrs, _parseSheetAttrs, _parseCalEventAttrs };
// 8 method bodies extracted to dedicated modules. AgentExecutor 의 동명 메서드는
// 이제 thin wrapper — deps 객체를 묶어서 free function 으로 위임.
import { callNonStreaming as callNonStreamingFn } from './agent/llm/callNonStreaming';
import { runMapReduce, shouldMapReduce } from './agent/handlePrompt/largeInputMapReduce';
import { createStreamingRequest as createStreamingRequestFn } from './agent/llm/createStreamingRequest';
import { streamChatOnce as streamChatOnceFn } from './agent/llm/streamChatOnce';
import { maybeEmitDevilRebuttal as maybeEmitDevilRebuttalFn } from './agent/llm/devilRebuttal';
@@ -768,12 +769,103 @@ export class AgentExecutor {
// Context budget computation → src/agent/handlePrompt/computeBudgetedRequest.ts
const imageCount = (reqMessages as any[])
.reduce((n, m) => n + (Array.isArray(m?.images) ? m.images.length : 0), 0);
// Budget against the model's REAL loaded window, not just the user's
// contextLength setting. Best-effort + cached; only for the LM Studio
// SDK path (REST/Ollama/cloud expose no such query → undefined → prior behavior).
let actualContextLength: number | undefined;
try {
const _isCloud = (() => {
try {
const { parseModelPrefix } = require('./features/providers') as typeof import('./features/providers');
return !!parseModelPrefix(actualModel);
} catch { return false; }
})();
if (!_isCloud
&& resolveEngine(ollamaUrl) === 'lmstudio'
&& this.options.lmStudioStreamer?.getModelContextLength) {
actualContextLength = await this.options.lmStudioStreamer.getModelContextLength(actualModel);
}
} catch { /* best-effort — fall back to configured window */ }
// ── Large-input Map-Reduce ────────────────────────────────────────
// When a SINGLE user message is too big to fit the (real) window,
// history-trimming can't help — you can't drop the current question.
// Chunk it, extract only the request-relevant facts per chunk, and
// integrate, then let the normal streaming path answer from the
// condensed context. Only the user-visible turn; casual chat skipped.
if (loopDepth === 0 && !isCasualConversation && config.largeInputMapReduce) {
try {
const effWindow = (typeof actualContextLength === 'number' && actualContextLength > 0)
? Math.min(config.contextLength, actualContextLength)
: config.contextLength;
const lastUserIdx = reqMessages.map((m) => m.role).lastIndexOf('user');
const lastUser = lastUserIdx >= 0 ? reqMessages[lastUserIdx] : undefined;
const content = typeof lastUser?.content === 'string' ? lastUser.content : '';
const sysTokens = estimateTokens(fullSystemPrompt) + 4;
const mrCfg = {
enabled: true,
triggerRatio: config.mapReduceTriggerRatio,
concurrency: config.mapReduceConcurrency,
maxDepth: config.mapReduceMaxDepth,
showProvenance: config.mapReduceShowProvenance,
};
if (lastUser && shouldMapReduce(estimateTokens(content), effWindow, mrCfg)) {
const intent = content.length > 1400
? `${content.slice(0, 800)}\n…\n${content.slice(-400)}`
: content;
const mrEngine = resolveEngine(ollamaUrl);
this.webview?.postMessage({ type: 'mapReduceStatus', value: { phase: 'start' } });
const mr = await runMapReduce(
{
callLLM: async (messages, maxTokens) => {
const r = await this.callNonStreaming({
baseUrl: ollamaUrl,
modelName: actualModel,
engine: mrEngine,
messages,
temperature: 0.1,
maxTokens,
contextLength: effWindow,
signal: this.abortController?.signal,
});
return r.text;
},
estimateTokens,
log: (msg, meta) => logInfo(msg, meta),
signal: this.abortController?.signal,
},
{ intent, largeContent: content, windowTokens: effWindow, systemTokens: sysTokens, safetyMargin: config.contextSafetyMargin, cfg: mrCfg },
);
// allIrrelevant → keep original (budgeter truncates) rather than forcing an empty context.
if (!mr.allIrrelevant && mr.condensedContext.trim()) {
reqMessages[lastUserIdx] = {
...lastUser,
content: `${intent}\n\n──────── 추출된 관련 자료 (원본 ${mr.chunkCount}조각 중 ${mr.relevantCount}조각, 통합 ${mr.reduceDepth}단계) ────────\n${mr.condensedContext}`,
} as any;
logInfo('Large input condensed via map-reduce.', {
model: actualModel, chunkCount: mr.chunkCount, relevantCount: mr.relevantCount, reduceDepth: mr.reduceDepth,
});
}
this.webview?.postMessage({
type: 'mapReduceStatus',
value: { phase: 'done', chunkCount: mr.chunkCount, relevantCount: mr.relevantCount, allIrrelevant: mr.allIrrelevant },
});
}
} catch (e: any) {
// Any failure → fall through to the normal (single-shot) path. Worst case the
// budgeter truncates the oversized input, which is the prior behavior.
logError('Large-input map-reduce failed — falling back to single-shot path.', { error: e?.message ?? String(e) });
this.webview?.postMessage({ type: 'mapReduceStatus', value: { phase: 'error' } });
}
}
const _budget = computeBudgetedRequest({
fullSystemPrompt,
reqMessages,
actualModel,
config,
imageCount,
actualContextLength,
});
const messagesForRequest = _budget.messagesForRequest;
const ctxLimits = _budget.ctxLimits;
@@ -819,6 +911,8 @@ export class AgentExecutor {
paramB: modelParamB,
contextLength: ctxLimits.contextLength,
nominalContextLength: config.contextLength,
actualContextLength,
windowMismatch: _budget.windowMismatch,
cappedForSmallModel,
inputTokens,
maxOutputTokens,
@@ -19,6 +19,13 @@ export interface ComputeBudgetedRequestInput {
/** Result of `getConfig()` — reads contextLength, maxOutputTokens, contextSafetyMargin, smallModelContextCap, autoCompactHistory. */
config: any;
imageCount: number;
/**
* The model's *actually-loaded* context window (LM Studio `getContextLength()`),
* when known. Budgeting uses the smaller of this and `config.contextLength` so we
* never overflow a model loaded with a smaller window than the user's setting.
* Omit (undefined) to budget against the configured value alone (prior behavior).
*/
actualContextLength?: number;
}
export interface ComputeBudgetedRequestResult {
@@ -34,6 +41,10 @@ export interface ComputeBudgetedRequestResult {
outputBudget: { maxOutputTokens: number; available: number; tight: boolean };
modelParamB: number | null;
cappedForSmallModel: boolean;
/** True when the model's real loaded window is smaller than `config.contextLength` (we clamped to the real one). */
windowMismatch: boolean;
/** The window actually used for budgeting (after real-window clamp + small-model cap). */
effectiveContextLength: number;
}
/**
@@ -60,15 +71,34 @@ export function computeBudgetedRequest(input: ComputeBudgetedRequestInput): Comp
// smaller effective window. Never applied to 4B+ models, and never when the setting is 0 —
// capping squeezes the output-token budget, so it's a knob, not a default.
const modelParamB = estimateModelParamsB(actualModel);
// The real ceiling is whatever window the model was actually loaded with — the
// server truncates anything past it. When known, clamp the configured setting
// down to it so we budget against the smaller of the two. (When unknown, keep
// the configured value — prior behavior.)
const actualWindow = (typeof input.actualContextLength === 'number'
&& Number.isFinite(input.actualContextLength)
&& input.actualContextLength > 0)
? input.actualContextLength
: undefined;
const configuredWindow = config.contextLength;
const windowMismatch = actualWindow !== undefined && actualWindow < configuredWindow;
const realWindow = actualWindow !== undefined ? Math.min(configuredWindow, actualWindow) : configuredWindow;
if (windowMismatch) {
logInfo('Model loaded with a smaller context window than the setting — clamping budget to the real window.', {
model: actualModel, configuredWindow, actualWindow,
});
}
const smallModelCap = config.smallModelContextCap; // 0 = disabled (default)
const cappedForSmallModel = smallModelCap > 0
&& modelParamB !== null && modelParamB <= 3
&& config.contextLength > smallModelCap;
const effectiveContextLength = cappedForSmallModel ? smallModelCap : config.contextLength;
&& realWindow > smallModelCap;
const effectiveContextLength = cappedForSmallModel ? smallModelCap : realWindow;
if (cappedForSmallModel) {
logInfo('Small model detected — capping effective context window for budgeting.', {
model: actualModel, paramB: modelParamB,
nominalContext: config.contextLength, effectiveContext: effectiveContextLength,
nominalContext: realWindow, effectiveContext: effectiveContextLength,
});
}
const ctxLimits: ContextLimits = {
@@ -157,5 +187,7 @@ export function computeBudgetedRequest(input: ComputeBudgetedRequestInput): Comp
outputBudget,
modelParamB,
cappedForSmallModel,
windowMismatch,
effectiveContextLength,
};
}
@@ -0,0 +1,265 @@
/**
* ============================================================
* Large-Input Map-Reduce (큰 입력 청킹 + 통합)
*
* 한 번에 컨텍스트 창에 안 들어가는 단일 사용자 입력(긴 회의록·리서치 덤프 등)을
* 1) 청크로 분할(Map 대상)
* 2) 각 청크에서 "요청과 관련된 사실만" 발췌 (질의 인지형 추출 — 일반 요약 X)
* 3) 발췌들을 통합(Reduce). 합본이 또 창을 넘으면 계층적으로 재통합.
* 한 뒤, 압축된 컨텍스트를 돌려줘 정상 스트리밍 경로가 최종 답변을 생성하게 한다.
*
* 신뢰성 원칙(ASTRA): 추측·창작 금지, 원문 표현 보존, 출처(`[조각 k]`) 태깅,
* 전부 무관하면 정직하게 "관련 내용 없음" 신호.
*
* LLM 호출은 `callLLM` 으로 주입 → 코어 로직은 네트워크 의존 없이 단위 테스트 가능.
* ============================================================
*/
import type { ChatMessage } from '../../agent';
import { splitIntoSections } from '../../retrieval/chunker';
export interface MapReduceConfig {
enabled: boolean;
/** 단일 입력 토큰 > (유효 창 × triggerRatio) 이면 발동. */
triggerRatio: number;
concurrency: number;
maxDepth: number;
showProvenance: boolean;
}
export interface MapReduceDeps {
/** 메시지 배열 → 모델 응답 텍스트. (callNonStreaming 래퍼) */
callLLM: (messages: ChatMessage[], maxTokens: number) => Promise<string>;
estimateTokens: (text: string) => number;
log?: (msg: string, meta?: Record<string, unknown>) => void;
signal?: AbortSignal;
}
export interface MapReduceParams {
/** 사용자 요청 의도 힌트 (보통 원본 입력의 머리/꼬리 발췌 — 지시문이 거기 있음). */
intent: string;
/** 청킹 대상이 되는 큰 본문. */
largeContent: string;
/** 유효 컨텍스트 창(토큰) — Phase 1 의 effectiveContextLength. */
windowTokens: number;
/** 시스템 프롬프트가 이미 차지한 토큰. */
systemTokens: number;
safetyMargin: number;
cfg: MapReduceConfig;
}
export interface MapReduceResult {
/** 통합된 관련 자료. 정상 경로에서 사용자 메시지 본문을 이걸로 대체. */
condensedContext: string;
chunkCount: number;
relevantCount: number;
reduceDepth: number;
/** 모든 청크가 무관 → 호출 측에서 정직한 에스컬레이션. */
allIrrelevant: boolean;
}
const IRRELEVANT_MARKER = '(관련 없음)';
/** 추출/통합 호출이 쓸 출력 토큰 상한 — 발췌는 원문보다 짧으므로 보수적으로. */
const EXTRACT_OUTPUT_TOKENS = 1024;
const REDUCE_OUTPUT_TOKENS = 2048;
/** 토큰→문자 환산(한국어 보수치 ~2자/토큰). 청크 크기 산정용. */
const CHARS_PER_TOKEN = 2;
/** 유효 창에서 입력에 쓸 수 있는 토큰 예산. computeBudgetedRequest 와 같은 공식. */
export function inputBudgetTokens(windowTokens: number, systemTokens: number, safetyMargin: number): number {
const outputReserve = Math.max(2048, Math.floor(windowTokens * 0.1));
return Math.max(256, windowTokens - systemTokens - outputReserve - safetyMargin);
}
/** 단일 입력이 map-reduce 대상인지. (cfg.enabled + 입력이 창의 triggerRatio 초과) */
export function shouldMapReduce(latestUserTokens: number, windowTokens: number, cfg: MapReduceConfig): boolean {
if (!cfg.enabled) return false;
if (windowTokens <= 0) return false;
return latestUserTokens > windowTokens * cfg.triggerRatio;
}
/** 한 청크가 (자기 + 추출 프롬프트 오버헤드 + 출력 예약)으로 창에 들어가도록 문자 상한 산정. */
export function chunkCharBudget(windowTokens: number, systemTokens: number, safetyMargin: number): number {
// 추출 프롬프트 자체 오버헤드(지시문 + intent) ~800 토큰 가정.
const promptOverhead = 800;
const perChunkTokenBudget = Math.max(
512,
windowTokens - systemTokens - safetyMargin - EXTRACT_OUTPUT_TOKENS - promptOverhead
);
// 보수적으로 70% 만 사용 (추정 오차 흡수).
return Math.floor(perChunkTokenBudget * CHARS_PER_TOKEN * 0.7);
}
function buildExtractPrompt(intent: string, chunkText: string, idx: number, total: number): ChatMessage[] {
const system = [
'너는 긴 자료에서 사용자 요청에 필요한 사실만 정확히 발췌하는 추출기다.',
'규칙:',
'1) 사용자 요청과 직접 관련된 사실·수치·발언·결정사항만 원문 표현 그대로 발췌한다.',
'2) 요약·추측·창작·일반화 금지. 자료에 없는 내용은 절대 만들지 않는다.',
`3) 이 조각에 관련 내용이 전혀 없으면 정확히 "${IRRELEVANT_MARKER}" 한 줄만 출력한다.`,
'4) 불릿(-)으로 간결하게. 각 항목은 자료에 근거해야 한다.',
].join('\n');
const user = [
`[사용자 요청 의도]\n${intent}`,
`\n[자료 조각 ${idx}/${total}]\n${chunkText}`,
`\n위 조각에서 요청 수행에 필요한 사실만 발췌하라. 없으면 "${IRRELEVANT_MARKER}".`,
].join('\n');
return [
{ role: 'system', content: system },
{ role: 'user', content: user },
];
}
function buildReducePrompt(intent: string, extractions: string): ChatMessage[] {
const system = [
'너는 여러 발췌를 중복 없이 하나로 통합하는 통합기다.',
'규칙: 발췌에 있는 사실만 유지하고, 중복은 병합한다. 추측·창작 금지.',
'원문 사실과 (있다면) [조각 k] 출처 표기를 보존한다.',
].join('\n');
const user = `[사용자 요청 의도]\n${intent}\n\n[발췌 모음]\n${extractions}\n\n위 발췌들을 요청 관점에서 중복 없이 통합하라.`;
return [
{ role: 'system', content: system },
{ role: 'user', content: user },
];
}
/** 동시성 제한 map. 순서 보존. */
async function mapWithConcurrency<T, R>(
items: T[],
limit: number,
fn: (item: T, index: number) => Promise<R>,
signal?: AbortSignal,
): Promise<R[]> {
const results: R[] = new Array(items.length);
let next = 0;
const n = Math.max(1, Math.min(limit, items.length));
const workers = Array.from({ length: n }, async () => {
while (true) {
if (signal?.aborted) return;
const i = next++;
if (i >= items.length) return;
results[i] = await fn(items[i], i);
}
});
await Promise.all(workers);
return results;
}
function isIrrelevant(text: string): boolean {
const t = (text || '').trim();
return t.length === 0 || t === IRRELEVANT_MARKER || /^\(?\s*관련\s*없음\s*\)?$/.test(t);
}
/**
* 큰 입력을 청크→추출→통합한다. 호출 측은 trigger 를 이미 통과시킨 뒤 호출한다고 가정하지만,
* 방어적으로 단일 청크면 추출만 하고 통합은 건너뛴다.
*/
export async function runMapReduce(deps: MapReduceDeps, params: MapReduceParams): Promise<MapReduceResult> {
const { intent, largeContent, windowTokens, systemTokens, safetyMargin, cfg } = params;
const log = deps.log ?? (() => {});
const targetChars = chunkCharBudget(windowTokens, systemTokens, safetyMargin);
const sections = splitIntoSections(largeContent, {
targetChars,
maxChars: targetChars * 2,
});
const chunks = sections.map((s) => s.text);
log('Map-reduce: split large input into chunks.', { chunkCount: chunks.length, targetChars });
// ── Map: 각 청크 → 질의 인지형 추출 ──────────────────────────────────
const extracted = await mapWithConcurrency(
chunks,
cfg.concurrency,
async (chunk, i) => {
if (deps.signal?.aborted) return '';
try {
const text = await deps.callLLM(
buildExtractPrompt(intent, chunk, i + 1, chunks.length),
EXTRACT_OUTPUT_TOKENS,
);
return text ?? '';
} catch (e: any) {
// 한 청크 실패가 전체를 막지 않게 — 원문 일부로 폴백(빈손보다 낫다).
log('Map-reduce: chunk extraction failed — falling back to truncated raw.', { chunk: i + 1, error: e?.message ?? String(e) });
return chunk.slice(0, targetChars);
}
},
deps.signal,
);
const relevant: string[] = [];
extracted.forEach((text, i) => {
if (isIrrelevant(text)) return;
relevant.push(cfg.showProvenance ? `[조각 ${i + 1}]\n${text.trim()}` : text.trim());
});
if (relevant.length === 0) {
log('Map-reduce: every chunk was irrelevant.', { chunkCount: chunks.length });
return { condensedContext: '', chunkCount: chunks.length, relevantCount: 0, reduceDepth: 0, allIrrelevant: true };
}
// ── Reduce: 합본이 입력 예산에 들어갈 때까지 계층적으로 통합 ──────────
const budget = inputBudgetTokens(windowTokens, systemTokens, safetyMargin);
// intent 분량 + 헤더 여유를 위해 예산의 80% 를 컨텍스트 상한으로.
const contextCeiling = Math.floor(budget * 0.8);
let current = relevant;
let depth = 0;
while (depth < cfg.maxDepth) {
const joined = current.join('\n\n');
if (deps.estimateTokens(joined) <= contextCeiling) break;
// 그룹으로 묶어 각 그룹을 통합 → 개수 감소.
const groups = groupToFit(current, deps.estimateTokens, contextCeiling);
if (groups.length >= current.length) break; // 더 못 줄임 — 마지막에 잘림 처리
log('Map-reduce: hierarchical reduce round.', { depth: depth + 1, from: current.length, to: groups.length });
current = await mapWithConcurrency(
groups,
cfg.concurrency,
async (group) => {
if (deps.signal?.aborted) return group.join('\n\n');
try {
return await deps.callLLM(buildReducePrompt(intent, group.join('\n\n')), REDUCE_OUTPUT_TOKENS);
} catch {
return group.join('\n\n'); // 통합 실패 → 원본 그룹 유지
}
},
deps.signal,
);
depth++;
}
let condensed = current.join('\n\n');
// maxDepth 도달했는데도 넘치면 하드 트렁케이트(서버 overflow 방지) + 경고는 호출 측에서.
if (deps.estimateTokens(condensed) > contextCeiling) {
const charCeiling = contextCeiling * CHARS_PER_TOKEN;
condensed = condensed.slice(0, charCeiling) + '\n\n[…자료가 많아 일부 생략됨]';
log('Map-reduce: reduce hit max depth and was hard-truncated.', { maxDepth: cfg.maxDepth });
}
return {
condensedContext: condensed,
chunkCount: chunks.length,
relevantCount: relevant.length,
reduceDepth: depth,
allIrrelevant: false,
};
}
/** 항목들을 순서대로 누적해 ceiling 을 넘기 직전까지 한 그룹으로 묶는다. */
function groupToFit(items: string[], estimate: (s: string) => number, ceiling: number): string[][] {
const groups: string[][] = [];
let cur: string[] = [];
let curTokens = 0;
for (const item of items) {
const t = estimate(item);
if (cur.length > 0 && curTokens + t > ceiling) {
groups.push(cur);
cur = [];
curTokens = 0;
}
cur.push(item);
curTokens += t;
}
if (cur.length > 0) groups.push(cur);
return groups;
}
+16
View File
@@ -40,6 +40,17 @@ export interface IAgentConfig {
autoCompactHistory: boolean;
/** 작은 모델(≤4B) 감지 시 예산 계산에 쓸 유효 context window 상한. 0 = 비활성화. */
smallModelContextCap: number;
// ─── 큰 입력 Map-Reduce (긴 회의록/리서치 덤프 청킹·통합) ───
/** 단일 사용자 입력이 창을 넘으면 청크→추출→통합으로 처리. 끄면 기존 단발 경로(잘릴 수 있음). */
largeInputMapReduce: boolean;
/** 단일 입력 토큰이 (유효 창 × 이 비율)을 넘으면 map-reduce 발동. 기본 0.6. */
mapReduceTriggerRatio: number;
/** 청크 추출 동시성. 로컬 단일 GPU 보호용으로 낮게. 기본 2. */
mapReduceConcurrency: number;
/** 추출 합본이 창을 넘을 때 계층적 통합 최대 깊이. 기본 3. */
mapReduceMaxDepth: number;
/** 최종 답변에 `[조각 k]` 출처 태그를 노출. 기본 false. */
mapReduceShowProvenance: boolean;
// ─── 응답 복구 (Thought Quarantine / Auto-Continuation) ───
/** 답변이 출력 토큰 한계에 걸리면 사용자 개입 없이 내부적으로 이어서 생성. */
autoContinueOnOutputLimit: boolean;
@@ -500,6 +511,11 @@ export function getConfig(): IAgentConfig {
})(),
autoCompactHistory: cfg.get<boolean>('autoCompactHistory', true),
smallModelContextCap: Math.max(0, cfg.get<number>('smallModelContextCap', 0)),
largeInputMapReduce: cfg.get<boolean>('largeInputMapReduce', true),
mapReduceTriggerRatio: Math.min(0.95, Math.max(0.3, cfg.get<number>('mapReduceTriggerRatio', 0.6))),
mapReduceConcurrency: Math.min(8, Math.max(1, cfg.get<number>('mapReduceConcurrency', 2))),
mapReduceMaxDepth: Math.min(6, Math.max(1, cfg.get<number>('mapReduceMaxDepth', 3))),
mapReduceShowProvenance: cfg.get<boolean>('mapReduceShowProvenance', false),
autoContinueOnOutputLimit: cfg.get<boolean>('autoContinueOnOutputLimit', true),
maxAutoContinuations: Math.max(0, Math.min(10, cfg.get<number>('maxAutoContinuations', 4))),
finalOnlyRetryOnThoughtLeak: cfg.get<boolean>('finalOnlyRetryOnThoughtLeak', true),
+45
View File
@@ -39,6 +39,17 @@ export interface ILMStudioClient {
* "Model is disposed!" or "lock() request could not be registered" error.
*/
getModelHandle(modelKey: string, options?: { refresh?: boolean }): Promise<LLM>;
/**
* The model's *actually-loaded* context window in tokens (LM Studio's
* `llm.getContextLength()`), or `undefined` if it can't be determined.
*
* The user-facing `g1nation.contextLength` setting is only a budgeting
* intent — the real ceiling is whatever window the model was loaded with.
* Budgeting against the larger of the two silently overflows the server,
* which then truncates the prompt or emits EOS as the first token (empty
* answer). Cached per-key because it only changes on reload.
*/
getModelContextLength(modelKey: string): Promise<number | undefined>;
isReachable(): Promise<boolean>;
setBaseUrl(httpBaseUrl: string): void;
}
@@ -84,8 +95,10 @@ export class LMStudioClient implements ILMStudioClient {
private _wsUrl: string | undefined;
private _loadedCache: { value: string[]; expiresAt: number } | undefined;
private _downloadedCache: { value: string[]; expiresAt: number } | undefined;
private _contextLengthCache = new Map<string, { value: number; expiresAt: number }>();
private static readonly DEFAULT_LOADED_CACHE_TTL_MS = 5000;
private static readonly DEFAULT_DOWNLOADED_CACHE_TTL_MS = 60_000;
private static readonly DEFAULT_CONTEXT_LENGTH_CACHE_TTL_MS = 60_000;
constructor(httpBaseUrl: string) {
this.setBaseUrl(httpBaseUrl);
@@ -98,6 +111,7 @@ export class LMStudioClient implements ILMStudioClient {
this._sdk = undefined;
this._loadedCache = undefined;
this._downloadedCache = undefined;
this._contextLengthCache.clear();
}
}
@@ -170,6 +184,7 @@ export class LMStudioClient implements ILMStudioClient {
invalidateCaches(): void {
this._loadedCache = undefined;
this._downloadedCache = undefined;
this._contextLengthCache.clear();
}
async listLoaded(): Promise<string[]> {
@@ -243,6 +258,36 @@ export class LMStudioClient implements ILMStudioClient {
}
}
async getModelContextLength(modelKey: string): Promise<number | undefined> {
const key = (modelKey || '').trim();
if (!key) return undefined;
const now = Date.now();
const cached = this._contextLengthCache.get(key);
if (cached && cached.expiresAt > now) return cached.value;
try {
// Reuses the same handle the stream will use. If the model isn't
// loaded yet this forces a JIT load — acceptable since the very next
// step streams from it anyway. Best-effort: any failure (incl. the
// load-coalescing "Operation canceled" race) falls back to undefined
// so the caller keeps the configured window.
const handle: any = await this.getSdk().llm.model(key);
const len = typeof handle?.getContextLength === 'function'
? await handle.getContextLength()
: undefined;
if (typeof len === 'number' && Number.isFinite(len) && len > 0) {
this._contextLengthCache.set(key, {
value: len,
expiresAt: now + LMStudioClient.DEFAULT_CONTEXT_LENGTH_CACHE_TTL_MS,
});
return len;
}
return undefined;
} catch (e: any) {
logError('Failed to query LM Studio model context length.', { modelKey: key, error: e?.message ?? String(e) });
return undefined;
}
}
async isReachable(): Promise<boolean> {
try {
await this.getSdk().llm.listLoaded();
+61 -12
View File
@@ -83,6 +83,12 @@ export interface IChatStreamer {
* silently-disposed handle that needs a fresh WebSocket round-trip.
*/
resetHandle?(modelName: string): Promise<void>;
/**
* The model's actually-loaded context window in tokens, or `undefined` if
* unavailable. Callers use this to budget against the real ceiling instead
* of the user's `contextLength` setting. Best-effort — never throws.
*/
getModelContextLength?(modelName: string): Promise<number | undefined>;
}
/**
@@ -115,7 +121,28 @@ export class LMStudioStreamer implements IChatStreamer {
// would duplicate tokens.
for (let attempt = 1; attempt <= 2; attempt++) {
const refresh = attempt > 1;
const model = await this.client.getModelHandle(trimmedModel, refresh ? { refresh: true } : undefined);
// Handle acquisition is guarded on its own: it happens BEFORE the
// stream try/catch below, so without this an "Operation canceled"
// (the lifecycle manager's concurrent load for this same model was
// superseded/aborted and the SDK coalesced our JIT lookup into that
// dead load), a disposed handle, or a dropped WebSocket would crash
// the whole turn with no retry. Large inputs make this far more
// likely: loading a big model to hold a large prompt is slow, which
// widens the window for a concurrent switch/abort to land mid-load.
let model: Awaited<ReturnType<ILMStudioClient['getModelHandle']>>;
try {
model = await this.client.getModelHandle(trimmedModel, refresh ? { refresh: true } : undefined);
} catch (acqErr: any) {
// Genuine user cancel — don't retry, just stop quietly.
if (req.signal?.aborted || acqErr?.name === 'AbortError') return;
const acqMsg = String(acqErr?.message ?? acqErr);
if (this.isTransientHandleError(acqMsg) && attempt === 1) {
logInfo('LM Studio model handle acquisition hit a transient error — retrying with a fresh SDK.', { model: trimmedModel, error: acqMsg });
continue; // attempt 2 passes { refresh: true } → recreates the SDK client
}
logError('LM Studio model handle acquisition failed.', { model: trimmedModel, error: acqMsg, attempt });
throw acqErr;
}
logInfo('LM Studio SDK chat stream started.', { model: trimmedModel, messageCount: req.messages.length, attempt });
// Sampling defaults match the historical glitch-suppression preset for small /
@@ -216,17 +243,7 @@ export class LMStudioStreamer implements IChatStreamer {
}
const errMsg = String(caught?.message ?? caught);
// Broaden the "handle is bound to a dead WebSocket binding" detection. All of
// these resolve with the same fix (recreate the SDK client so the next
// llm.model() lookup mints a fresh handle).
const handleDead =
/\bdisposed\b/i.test(errMsg)
|| /lock\(\) request could not be registered/i.test(errMsg)
|| /channel\s+closed/i.test(errMsg)
|| /WebSocket\s+(?:is\s+not\s+open|closed|disconnected)/i.test(errMsg)
|| /Connection\s+(?:lost|reset|closed)/i.test(errMsg)
|| /\bECONNRESET\b/i.test(errMsg)
|| /socket\s+hang\s*up/i.test(errMsg);
const handleDead = this.isTransientHandleError(errMsg);
if (handleDead && yielded === 0 && attempt === 1) {
logInfo('Dead LM Studio handle detected — retrying with a fresh SDK.', { model: trimmedModel, error: errMsg });
@@ -238,6 +255,38 @@ export class LMStudioStreamer implements IChatStreamer {
}
}
/**
* True when an error message indicates the SDK handle / WebSocket binding is
* dead, or its in-flight (coalesced) load was canceled out from under us —
* all fixable by recreating the SDK client so the next `llm.model()` lookup
* mints a fresh handle. Deliberately excludes genuine user aborts, which are
* caught earlier via `req.signal.aborted` / `AbortError` before reaching here.
*/
private isTransientHandleError(errMsg: string): boolean {
return (
/\bdisposed\b/i.test(errMsg)
|| /lock\(\) request could not be registered/i.test(errMsg)
|| /channel\s+closed/i.test(errMsg)
|| /WebSocket\s+(?:is\s+not\s+open|closed|disconnected)/i.test(errMsg)
|| /Connection\s+(?:lost|reset|closed)/i.test(errMsg)
|| /\bECONNRESET\b/i.test(errMsg)
|| /socket\s+hang\s*up/i.test(errMsg)
// The lifecycle manager's load got superseded/aborted and the SDK
// coalesced our JIT model() lookup into that canceled load.
|| /\boperation\s+cancell?ed\b/i.test(errMsg)
);
}
async getModelContextLength(modelName: string): Promise<number | undefined> {
const trimmed = (modelName || '').trim();
if (!trimmed) return undefined;
try {
return await this.client.getModelContextLength(trimmed);
} catch {
return undefined; // best-effort — caller falls back to the configured window
}
}
async resetHandle(modelName: string): Promise<void> {
const trimmed = (modelName || '').trim();
if (!trimmed) return;